Recent years have witnessed significant advancements in deep learning, machine learning, as well as artificial intelligence (AI) in general. The new methods and techniques brought by these advancements are transforming geospatial research in a variety of areas. For example, recent studies have shown deep learning techniques coupled with volunteered geographic information (such as OpenStreetMap data) can accurately extract buildings from satellite images for humanitarian mapping. Artificial intelligence methods are also enabling self-driving cars and intelligent transport system by analyzing large amounts of geographic information gathered by traffic cameras and sensors in real time. Many deep learning and machine learning techniques have facilitated natural language processing and have helped discover new knowledge from (geotagged)natural language texts. There also exist many other applications of deep learning and machine learning in geospatial research, such as spatial diffusion prediction in epidemiology, urban expansion analysis, and hyperspectral image analysis. In this context, we organize a special symposium focusing on the current status, recent advances, and possible future directions of this exciting research theme at the 2018 AAG Annual meeting, April 10-14, New Orleans, Louisiana. We aim to bring in geographers, GI scientists, spatial modeling experts, computer scientists, spatial data scientists, epidemiologists, urban planners, transportation professionals, and many others to discuss this rapidly developing research frontier.
|Presenter||Maosheng Hu*, China University of Geosciences(Wuhan), Annotation recognition from digital maps using deep learning without segmentation||20||8:00 AM|
|Presenter||Huan Ning*, University of South Carolina, Zhenlong Li, University of South Carolina, Build customized deep learning training dataset for remote sensing image classification||20||8:20 AM|
|Presenter||Chang Zhao*, University of Iowa, Caglar Koylu, University of Iowa, Heather Sander, University of Iowa, Using deep learning and kernel density estimation for detecting spatio-temporal footprints of birdwatchers on Flickr||20||8:40 AM|
|Presenter||Jacob Arndt*, , Eric Shook, University of Minnesota, Exploring New Spatial Approaches Toward Deep Learning for Satellite Image Classification||20||9:00 AM|
To access contact information login